Abstract: In general, the invention is directed to techniques for reducing deadlocks that may arise when performing fabric replication. For example, as described herein, a network device includes packet replicators that each comprises a plurality of resource partitions. A replication data structure for a packet received by the network device includes packet replicator nodes that are arranged hierarchically to occupy one or more levels of the replication data structure. Each of the resource partitions in each of the plurality of packet replicators is associated with a different level of the replication data structure. The packet replicators replicate the packet according to the replication data structure, and each of the packet replicators handles the packet using the one of the resource partitions of the packet replicator that is associated with the level of the replication data structure occupied by the node that corresponds to that particular packet replicator.

Abstract: A mesh network of wired and/or wireless nodes is described in which a centralized controller provides seamless end-to-end service from the edge of the mesh network to mesh nodes located proximate to subscriber devices. The controller operates to provide a central configuration point for configuring forwarding planes of the mesh nodes of the mesh network, so as to set up transport data channels to transport traffic from the edge nodes via the mesh nodes to the subscriber devices.

Abstract: A high-performance, scalable and drop-free data center switch fabric and infrastructure is described. The data center switch fabric may leverage low cost, off-the-shelf packet-based switching components (e.g., IP over Ethernet (IPoE)) and overlay forwarding technologies rather than proprietary switch fabric. In one example, host network accelerators (HNAs) are positioned between servers (e.g., virtual machines or dedicated servers) of the data center and an IPoE core network that provides point-to-point connectivity between the servers. The HNAs are hardware devices that embed virtual routers on one or more integrated circuits, where the virtual router are configured to extend the one or more virtual networks to the virtual machines and to seamlessly transport packets over the switch fabric using an overlay network. In other words, the HNAs provide hardware-based, seamless access interfaces to overlay technologies used for communicating packet flows through the core switching network of the data center.

Abstract: Methods and devices for processing packets are provided. The processing device may Include an input interface for receiving data units containing header information of respective packets; a first module configurable to perform packet filtering based on the received data units; a second module configurable to perform traffic analysis based on the received data units; a third module configurable to perform load balancing based on the received data units; and a fourth module configurable to perform route lookups based on the received data units.

Abstract: A first network client requests initiation of a data transfer with a second network client. An admission control facility (ACF) responds to the initiation request by performing admission analysis to determine whether to initiate the data transfer. The ACF sends one or more packets to the second network client. In response, the second network client sends acknowledgment packets back to the ACF. The ACF performs admission analysis based on the packets sent and the acknowledgment packets, and determines whether the data transfer should be initiated based on the analysis. The admission analysis may be based on a variety of factors, such as the average time to receive an acknowledgment for each packet, the variance of the time to receive an acknowledgment for each packet, a combination of these factors, or a combination of these and other factors.

Abstract: Dynamic control channel establishment for an access network is described in which a centralized controller provides seamless end-to-end service from a core-facing edge of a network to access nodes. For example, a method includes receiving, by the centralized controller, a discover message originating from a network node, which includes an intermediate node list that specifies a plurality of network nodes the discover message traversed from the network node to an edge node, determining, based on the plurality of nodes specified by the discover message, a path from the edge node to the network node, allocating each of a plurality of Multi-protocol Label Switching (MPLS) labels to a respective outgoing interface of each of the plurality of network nodes, and outputting one or more control messages for configuring the network node, wherein the control messages are encapsulated within a label stack comprising the allocated plurality of labels.

Abstract: A high-performance, scalable and drop-free data center switch fabric and infrastructure is described. The data center switch fabric may leverage low cost, off-the-shelf packet-based switching components (e.g., IP over Ethernet (IPoE)) and overlay forwarding technologies rather than proprietary switch fabric. In one example, host network accelerators (HNAs) are positioned between servers (e.g., virtual machines or dedicated servers) of the data center and an IPoE core network that provides point-to-point connectivity between the servers. The HNAs are hardware devices that embed virtual routers on one or more integrated circuits, where the virtual router are configured to extend the one or more virtual networks to the virtual machines and to seamlessly transport packets over the switch fabric using an overlay network. In other words, the HNAs provide hardware-based, seamless access interfaces to overlay technologies used for communicating packet flows through the core switching network of the data center.

Abstract: A high-performance, scalable and drop-free data center switch fabric and infrastructure is described. The data center switch fabric may leverage low cost, off-the-shelf packet-based switching components (e.g., IP over Ethernet (IPoE)) and overlay forwarding technologies rather than proprietary switch fabric. In one example, host network accelerators (HNAs) are positioned between servers (e.g., virtual machines or dedicated servers) of the data center and an IPoE core network that provides point-to-point connectivity between the servers. The HNAs are hardware devices that embed virtual routers on one or more integrated circuits, where the virtual router are configured to extend the one or more virtual networks to the virtual machines and to seamlessly transport packets over the switch fabric using an overlay network. In other words, the HNAs provide hardware-based, seamless access interfaces to overlay technologies used for communicating packet flows through the core switching network of the data center.

Abstract: A high-performance, scalable and drop-free data center switch fabric and infrastructure is described. The data center switch fabric may leverage low cost, off-the-shelf packet-based switching components (e.g., IP over Ethernet (IPoE)) and overlay forwarding technologies rather than proprietary switch fabric. In one example, host network accelerators (HNAs) are positioned between servers (e.g., virtual machines or dedicated servers) of the data center and an IPoE core network that provides point-to-point connectivity between the servers. The HNAs are hardware devices that embed virtual routers on one or more integrated circuits, where the virtual router are configured to extend the one or more virtual networks to the virtual machines and to seamlessly transport packets over the switch fabric using an overlay network. In other words, the HNAs provide hardware-based, seamless access interfaces to overlay technologies used for communicating packet flows through the core switching network of the data center.

Abstract: A high-performance, scalable and drop-free data center switch fabric and infrastructure is described. The data center switch fabric may leverage low cost, off-the-shelf packet-based switching components (e.g., IP over Ethernet (IPoE)) and overlay forwarding technologies rather than proprietary switch fabric. In one example, host network accelerators (HNAs) are positioned between servers (e.g., virtual machines or dedicated servers) of the data center and an IPoE core network that provides point-to-point connectivity between the servers. The HNAs are hardware devices that embed virtual routers on one or more integrated circuits, where the virtual router are configured to extend the one or more virtual networks to the virtual machines and to seamlessly transport packets over the switch fabric using an overlay network. In other words, the HNAs provide hardware-based, seamless access interfaces to overlay technologies used for communicating packet flows through the core switching network of the data center.

Abstract: In some embodiments, an apparatus comprises a core network node configured to be operatively coupled to a set of network nodes. The core network node is configured to receive a broadcast signal from a network node from the set of network nodes, which is originated from a host device operatively coupled to the network node. The broadcast signal is sent via a tunnel from the network node to the core network node, such that other network nodes that are not included in the tunnel do not receive the broadcast signal. The core network node is configured to retrieve control information associated with the broadcast signal without sending another broadcast signal, and then send the control information to the network node.

Abstract: In some embodiments, an apparatus includes an optical transceiver system that includes a set of optical transmitters and a backup optical transmitter. In such embodiments, each optical transmitter from the set of optical transmitter can transmit at a unique wavelength from a set of wavelengths. The backup optical transmitter can transmit at a wavelength from the set of wavelengths when an optical transmitter from the set of optical transmitters associated with that wavelength fails. In other embodiments, an apparatus includes an optical transceiver system that includes a set of optical receivers and a backup optical receiver. The backup optical receiver can receive at a wavelength from the set of wavelengths when an optical receiver from the set of optical receivers associated with that wavelength fails.

Abstract: A system provides congestion control and includes multiple queues that temporarily store data and a drop engine. The system associates a value with each of the queues, where each of the values relates to an amount of memory associated with the queue. The drop engine compares the value associated with a particular one of the queues to one or more programmable thresholds and selectively performs explicit congestion notification or packet dropping on data in the particular queue based on a result of the comparison.

Abstract: A system selectively drops data from queues. The system includes a drop table that stores drop probabilities. The system selects one of the queues to examine and generates an index into the drop table to identify one of the drop probabilities for the examined queue. The system then determines whether to drop data from the examined queue based on the identified drop probability.

Abstract: In general, the invention is directed to techniques for reducing deadlocks that may arise when performing fabric replication. For example, as described herein, a network device includes packet replicators that each comprises a plurality of resource partitions. A replication data structure for a packet received by the network device includes packet replicator nodes that are arranged hierarchically to occupy one or more levels of the replication data structure. Each of the resource partitions in each of the plurality of packet replicators is associated with a different level of the replication data structure. The packet replicators replicate the packet according to the replication data structure, and each of the packet replicators handles the packet using the one of the resource partitions of the packet replicator that is associated with the level of the replication data structure occupied by the node that corresponds to that particular packet replicator.

Abstract: Dynamic control channel establishment for an access network is described in which a centralized controller provides seamless end-to-end service from a core-facing edge of a network to access nodes. For example, a method includes receiving, by the centralized controller, a discover message originating from a network node, which includes an intermediate node list that specifies a plurality of network nodes the discover message traversed from the network node to an edge node, determining, based on the plurality of nodes specified by the discover message, a path from the edge node to the network node, allocating each of a plurality of Multi-protocol Label Switching (MPLS) labels to a respective outgoing interface of each of the plurality of network nodes, and outputting one or more control messages for configuring the network node, wherein the control messages are encapsulated within a label stack comprising the allocated plurality of labels.

Abstract: Subscriber management and network service integration for an access network is described in which a centralized controller provides seamless end-to-end service from a network to access nodes. For example, a method includes dynamically establishing a control channel between the centralized controller and an access node, and establishing a transport label switched path (LSP) transport network packets between the access node and the network node. The access node sends, via the control channel, an endpoint indication message that indicates that an endpoint that has joined the network at the access node. The access node receives a pseudo wire request message via the control channel to install forwarding state for creating a pseudo wire for providing one or more network services to the endpoint. The access node receives a direct switch message via the control channel to configure the access node to map traffic received from the endpoint to the pseudo wire.

Abstract: Dynamic control channel establishment for an access network is described in which a centralized controller provides seamless end-to-end service from a core-facing edge of a network to access nodes. For example, a method includes receiving, by the centralized controller, a discover message originating from a network node, which includes an intermediate node list that specifies a plurality of network nodes the discover message traversed from the network node to an edge node, determining, based on the plurality of nodes specified by the discover message, a path from the edge node to the network node, allocating each of a plurality of Multi-protocol Label Switching (MPLS) labels to a respective outgoing interface of each of the plurality of network nodes, and outputting one or more control messages for configuring the network node, wherein the control messages are encapsulated within a label stack comprising the allocated plurality of labels.

Abstract: In one embodiment, a method can include receiving at an egress schedule module a request to schedule transmission of a group of cells from an ingress queue through a switch fabric of a multi-stage switch. The ingress queue can be associated with an ingress stage of the multi-stage switch. The egress schedule module can be associated with an egress stage of the multi-stage switch. The method can also include determining, in response to the request, that an egress port at the egress stage of the multi-stage switch is available to transmit the group of cells from the multi-stage switch.

Abstract: In one embodiment, a method includes sending a first flow control signal to a first stage of transmit queues when a receive queue is in a congestion state. The method also includes sending a second flow control signal to a second stage of transmit queues different from the first stage of transmit queues when the receive queue is in the congestion state.